Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1657 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.5349. Min Act: -0.0001

Data Index: 842066 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.4951. Min Act: -0.0001

Data Index: 743375 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.4902. Min Act: -0.0001

Data Index: 1106133 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.3708. Min Act: -0.0001

Data Index: 1090914 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.4367. Min Act: -0.0001

Data Index: 1005910 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.3351. Min Act: -0.0001

Data Index: 630643 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.2919. Min Act: -0.0001

Data Index: 1278996 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.2496. Min Act: -0.0001

Data Index: 409850 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.3130. Min Act: -0.0000

Data Index: 1192859 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.2993. Min Act: -0.0001

Data Index: 297824 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.2510. Min Act: -0.0000

Data Index: 535246 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.2127. Min Act: -0.0001

Data Index: 491645 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.1874. Min Act: -0.0001

Data Index: 503040 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.1512. Min Act: -0.0001

Data Index: 430387 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.0730. Min Act: -0.0001

Data Index: 787651 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.1491. Min Act: -0.0001

Data Index: 463042 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.2145. Min Act: -0.0001

Data Index: 988002 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.1126. Min Act: -0.0001

Data Index: 1263898 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.0449. Min Act: -0.0001

Data Index: 1077349 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.5349. Min Range: -1.5349

Max Act: 1.0672. Min Act: -0.0001

Data Index: 264906 (C4 (Web Text))

Max Activating Token Index: 134